© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7968
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significance, importance, or a point of view.

    oai_token-act-pair · gemini-2.0-flash

    words related to lack or deficiency

    np_token-act-pair-logits · gpt-4o-mini

    absence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     them
    -1.37
    them
    -1.02
     it
    -0.96
     him
    -0.92
    これを
    -0.91
    それを
    -0.88
     그것
    -0.87
     AssemblyVersion
    -0.86
     इसे
    -0.86
     ihn
    -0.85
    POSITIVE LOGITS
    ؤلاء
    0.40
    liothèque
    0.40
    Życiorys
    0.40
    jointe
    0.40
    sendRedirect
    0.39
    windowFixed
    0.38
    .
    0.38
    Atoi
    0.37
    達は
    0.37
    ż
    0.36
    Activations Density 5.994%

    No Known Activations